• The Journal of the Acoustical Society of Korea
• /
• v.22 no.3
• /
• pp.194-201
• /
• 2003

In speech recognition, confidence measuring is to decide whether it can be accepted as the recognized results or not. The confidence is measured by integrating frames into phone and word level. In case of word recognition, the confidence measuring verifies the results of recognition and Out-Of-Vocabulary (OOV). Therefore, the post-processing could improve the performance of recognizer without accepting it as a recognition error. In this paper, we measure the confidence modifying log likelihood ratio (LLR) which was the previous confidence measuring. It accumulates only those which the log likelihood ratio is negative when integrating the confidence to phone level from frame level. When comparing the verification performance for the results of word recognizer with the previous method, the FAR (False Acceptance Ratio) is decreased about 3.49% for the OOV and 15.25% for the recognition error when CAR (Correct Acceptance Ratio) is about 90%.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.10
• /
• pp.797-802
• /
• 2016

This paper proposes a noble voice recognition method based on an adaptive MFCC and deep learning for embedded systems. To enhance the recognition ratio of the proposed voice recognizer, ambient noise mixed into the voice signal has to be eliminated. However, noise filtering processes, which may damage voice data, diminishes the recognition ratio. In this paper, a filter has been designed for the frequency range within a voice signal, and imposed weights are used to reduce data deterioration. In addition, a deep learning algorithm, which does not require a database in the recognition algorithm, has been adapted for embedded systems, which inherently require small amounts of memory. The experimental results suggest that the proposed deep learning algorithm and HMM voice recognizer, utilizing the proposed adaptive MFCC algorithm, perform better than conventional MFCC algorithms in its recognition ratio within a noisy environment.

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.224-237
• /
• 2020

Recognition of banknote serial number is one of the important functions for intelligent banknote counter implementation and can be used for various purposes. However, the previous character recognition method is limited to use due to the font type of the banknote serial number, the variation problem by the solid status, and the recognition speed issue. In this paper, we propose an aspect ratio based character region segmentation and a convolutional neural network (CNN) based banknote serial number recognition method. In order to detect the character region, the character area is determined based on the aspect ratio of each character in the serial number candidate area after the banknote area detection and de-skewing process is performed. Then, we designed and compared four types of CNN models and determined the best model for serial number recognition. Experimental results showed that the recognition accuracy of each character was 99.85%. In addition, it was confirmed that the recognition performance is improved as a result of performing data augmentation. The banknote used in the experiment is Indian rupee, which is badly soiled and the font of characters is unusual, therefore it can be regarded to have good performance. Recognition speed was also enough to run in real time on a device that counts 800 banknotes per minute.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.9
• /
• pp.554-559
• /
• 2003

In this paper the possibility of snorer-dependent snore recognition using cepstral coefficients was suggested. We assumed that snore and speech sounds have some similarities and we used cepstral coefficients which are widely used for speech recognition. Snoring data were acquired from 18 persons including 5 patients diagnosed as snore patient. To evaluate the performance of proposed method, the distance ratio based on LPC cepstral coefficients was selected as an index for snorer-dependent snore recognition. As a result, distance ratio of 3 was selected as optimal value showing the most efficient snorer-dependent snore recognition, which is high accuracy of 95.05％ on average. In conclusion, the proposed method showed the possibilities to be applied in clinical applications for snorer-dependent snore recognition.

• Journal of Korea Multimedia Society
• /
• v.20 no.1
• /
• pp.17-31
• /
• 2017

The aim of the paper is to present an object recognition method toward augmented reality system that utilizes existing education instruments that was designed without any consideration on image processing and recognition. The light reflection, sizes, shapes, and color range of the existing target education instruments are major hurdles to our object recognition. In addition, the real-time performance requirements on embedded devices and user experience constraints for children users are quite challenging issues to be solved for our image processing and object recognition approach. In order to meet these requirements we employed a method cascading light-weight weak classification methods that are complimentary each other to make a resultant complicated and highly accurate object classifier toward practically reasonable precision ratio. We implemented the proposed method and tested the performance by video with more than 11,700 frames of actual playing scenario. The experimental result showed 0.54% miss ratio and 1.35% false hit ratio.

• Proceedings of the IEEK Conference
• /
• 2003.11b
• /
• pp.195-198
• /
• 2003

The accuracy of automatic speech recognition system depends on the presence of background noise and speaker variability such as sex, intonation of speech, and speaking rate. Specially, the speaking rate of both inter-speaker and intra-speaker is a serious cause of mis-recognition. In this paper, we propose the compensation method of the speaking rate by the ratio of each vowel's length in a phrase. First the number of feature vectors in a phrase is estimated by the information of speaking rate. Second, the estimated number of feature vectors is assigned to each syllable of the phrase according to the ratio of its vowel length. Finally, the process of feature vector extraction is operated by the number that assigned to each syllable in the phrase. As a result the accuracy of automatic speech recognition was improved using the proposed compensation method of the speaking rate.

• Proceedings of the KSPS conference
• /
• 2005.04a
• /
• pp.99-102
• /
• 2005

Research efforts have been made for out-of-vocabulary word rejection to improve the confidence of speech recognition systems. However, little attention has been paid to non-recognition sentence rejection. According to the appearance of pronunciation correction systems using speech recognition technology, it is needed to reject non-recognition sentences to provide users with more accurate and robust results. In this paper, we introduce standard phoneme based sentence rejection system with no need of special filler models. Instead we used word spotting ratio to determine whether input sentences would be accepted or rejected. Experimental results show that we can achieve comparable performance using only standard phoneme based recognition network in terms of the average of FRR and FAR.

• MALSORI
• /
• no.59
• /
• pp.27-51
• /
• 2006

For speech recognition systems, rejection function as well as decoding function is necessary to improve the reliability. There have been many research efforts on out-of-vocabulary word rejection, however, little attention has been paid on non-target sentence rejection. Recently pronunciation approaches using speech recognition increase the need for non-target sentence rejection to provide more accurate and robust results. In this paper, we proposed filler model method and word/phoneme detection ratio method to implement non-target sentence rejection system. We made performance evaluation of filler model along to word-level, phoneme-level, and sentence-level filler models respectively. We also perform the similar experiment using word-level and phoneme-level word/phoneme detection ratio method. For the performance evaluation, the minimized average of FAR and FRR is used for comparing the effectiveness of each method along with the number of words of given sentences. From the experimental results, we got to know that word-level method outperforms the other methods, and word-level filler mode shows slightly better results than that of word detection ratio method.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.5 no.2
• /
• pp.57-66
• /
• 2010

In this paper, we propose an enhanced voice recognition algorithm using adaptive MFCC(Mel Frequency Cepstral Coefficients) and neural network. Though it is very important to extract voice data from the raw data to enhance the voice recognition ratio, conventional algorithms are subject to deteriorating voice data when they eliminate noise within special frequency band. Differently from the conventional MFCC, the proposed algorithm imposed bigger weights to some specified frequency regions and unoverlapped filterbank to enhance the recognition ratio without deteriorating voice data. In simulation results, the proposed algorithm shows better performance comparing with MFCC since it is robust to variation of the environment.

• Phonetics and Speech Sciences
• /
• v.3 no.1
• /
• pp.117-123
• /
• 2011

Most individuals with hearing impairment have difficulty in understanding speech in noisy situations. This study was conducted to investigate sentence recognition ability using the Korean Standard-Sentence Lists for Preschoolers (KS-SL-P2) in pre-school age children with cochlear implants and hearing aids. The subjects of this study were 10 pre-school age children with hearing aids, 12 pre-school age children with cochlear implants, and 10 pre-school age children with normal hearing. Three kinds of signal-to-noise (SNR) conditions (+10 dB, +5 dB, 0 dB) were applied. The results for all pre-school age children with cochlear implants and hearing aids presented a significant increase in the score for sentence recognition as SNR increased. The sentence recognition score in speech noise were obtained with the SNR +10 dB. Significant differences existed between groups in terms of their sentence recognition ability, with the cochlear implant group performing better than the hearing aid group. These findings suggest the presence of a sentence recognition test using speech noise is useful for evaluating pre-school age children's listening skill.